中文
相关论文

相关论文: On the Effective Horizon of Inverse Reinforcement …

200 篇论文

Inverse reinforcement learning (IRL) denotes a powerful family of algorithms for recovering a reward function justifying the behavior demonstrated by an expert agent. A well-known limitation of IRL is the ambiguity in the choice of the…

机器学习 · 计算机科学 2023-04-26 Alberto Maria Metelli , Filippo Lazzati , Marcello Restelli

In this work, we study an inverse reinforcement learning (IRL) problem where the experts are planning under a shared reward function but with different, unknown planning horizons. Without the knowledge of discount factors, the reward…

机器学习 · 计算机科学 2024-09-27 Jiayu Yao , Weiwei Pan , Finale Doshi-Velez , Barbara E Engelhardt

Many imitation learning (IL) algorithms use inverse reinforcement learning (IRL) to infer a reward function that aligns with the demonstration. However, the inferred reward functions often fail to capture the underlying task objectives. In…

机器学习 · 计算机科学 2024-11-01 Weichao Zhou , Wenchao Li

Explicit engineering of reward functions for given environments has been a major hindrance to reinforcement learning methods. While Inverse Reinforcement Learning (IRL) is a solution to recover reward functions from demonstrations only,…

机器学习 · 计算机科学 2020-02-24 David Venuto , Jhelum Chakravorty , Leonard Boussioux , Junhao Wang , Gavin McCracken , Doina Precup

Inverse reinforcement learning (IRL) addresses the problem of recovering a task description given a demonstration of the optimal policy used to solve such a task. The optimal policy is usually provided by an expert or teacher, making IRL…

机器学习 · 计算机科学 2012-02-09 Héctor Ratia , Luis Montesano , Ruben Martinez-Cantin

Inverse reinforcement learning (IRL) aims to learn a reward function and a corresponding policy that best fit the demonstrated trajectories of an expert. However, current IRL works cannot learn incrementally from an ongoing trajectory…

机器学习 · 计算机科学 2025-07-24 Shicheng Liu , Minghui Zhu

Inverse reinforcement learning (IRL) is the problem of finding a reward function that generates a given optimal policy for a given Markov Decision Process. This paper looks at an algorithmic-independent geometric analysis of the IRL problem…

机器学习 · 计算机科学 2021-02-19 Abi Komanduru , Jean Honorio

Inverse reinforcement learning (IRL) is an imitation learning approach to learning reward functions from expert demonstrations. Its use avoids the difficult and tedious procedure of manual reward specification while retaining the…

机器学习 · 计算机科学 2024-03-25 Daulet Baimukashev , Gokhan Alcan , Ville Kyrki

Inverse Reinforcement Learning (IRL) -- the problem of learning reward functions from demonstrations of an \emph{expert policy} -- plays a critical role in developing intelligent systems. While widely used in applications, theoretical…

机器学习 · 统计学 2024-02-13 Lei Zhao , Mengdi Wang , Yu Bai

Inverse reinforcement learning (IRL) infers a reward function from demonstrations, allowing for policy improvement and generalization. However, despite much recent interest in IRL, little work has been done to understand the minimum set of…

机器学习 · 计算机科学 2019-08-19 Daniel S. Brown , Scott Niekum

Inverse reinforcement learning (IRL) seeks to infer a cost function that explains the underlying goals and preferences of expert demonstrations. This paper presents receding horizon inverse reinforcement learning (RHIRL), a new IRL…

机器学习 · 计算机科学 2022-10-18 Yiqing Xu , Wei Gao , David Hsu

Inverse Reinforcement Learning (IRL) has demonstrated effectiveness in a variety of imitation tasks. In this paper, we introduce an IRL framework designed to extract rewarding features from expert trajectories affected by delayed…

机器学习 · 计算机科学 2024-12-05 Simon Sinong Zhan , Qingyuan Wu , Zhian Ruan , Frank Yang , Philip Wang , Yixuan Wang , Ruochen Jiao , Chao Huang , Qi Zhu

A significant challenge for the practical application of reinforcement learning in the real world is the need to specify an oracle reward function that correctly defines a task. Inverse reinforcement learning (IRL) seeks to avoid this…

机器学习 · 计算机科学 2019-10-16 Kelvin Xu , Ellis Ratner , Anca Dragan , Sergey Levine , Chelsea Finn

Inverse reinforcement learning (IRL) aims to recover the reward function and the associated optimal policy that best fits observed sequences of states and actions implemented by an expert. Many algorithms for IRL have an inherently nested…

机器学习 · 计算机科学 2022-11-02 Siliang Zeng , Chenliang Li , Alfredo Garcia , Mingyi Hong

Inverse Reinforcement Learning (IRL) is the problem of finding a reward function which describes observed/known expert behavior. The IRL setting is remarkably useful for automated control, in situations where the reward function is…

机器学习 · 计算机科学 2022-09-12 Gregory Dexter , Kevin Bello , Jean Honorio

The gloabal objective of inverse Reinforcement Learning (IRL) is to estimate the unknown cost function of some MDP base on observed trajectories generated by (approximate) optimal policies. The classical approach consists in tuning this…

机器学习 · 计算机科学 2021-05-26 Firas Jarboui , Vianney Perchet

Inverse reinforcement learning (IRL) deals with estimating an agent's utility function from its actions. In this paper, we consider how an agent can hide its strategy and mitigate an adversarial IRL attack; we call this inverse IRL (I-IRL).…

机器学习 · 计算机科学 2022-05-24 Kunal Pattanayak , Vikram Krishnamurthy , Christopher Berry

Reinforcement learning in complex environments is a challenging problem. In particular, the success of reinforcement learning algorithms depends on a well-designed reward function. Inverse reinforcement learning (IRL) solves the problem of…

机器学习 · 计算机科学 2021-01-20 Rakhoon Hwang , Hanjin Lee , Hyung Ju Hwang

Inverse reinforcement learning (IRL) aims to recover the reward function of an expert agent from demonstrations of behavior. It is well-known that the IRL problem is fundamentally ill-posed, i.e., many reward functions can explain the…

机器学习 · 计算机科学 2024-06-07 Filippo Lazzati , Mirco Mutti , Alberto Maria Metelli

The inverse reinforcement learning approach to imitation learning is a double-edged sword. On the one hand, it can enable learning from a smaller number of expert demonstrations with more robustness to error compounding than behavioral…

机器学习 · 计算机科学 2024-06-06 Juntao Ren , Gokul Swamy , Zhiwei Steven Wu , J. Andrew Bagnell , Sanjiban Choudhury
‹ 上一页 1 2 3 10 下一页 ›